Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385484672> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4385484672 abstract "Over the past decade there has been efforts to address a major issue in obtaining high-performing Machine Learning (ML) models; that of more systematic methods to establish the optimal hyper-parameters for learning involving automated hyper-parameter selection which would increase the accuracy of these ML models. These methods have largely been driven by the popularity of the development of deep learning models, and traditional ML models have also benefited from these advances. One class of ML models where these hyper-parameter optimization techniques have rarely been applied is to a class of neural-network based learners called Evolving-Connectionist Systems (ECoS). To determine whether ECoS-based learners could improve their performance by benefitting from such hyper-parameter optimization methods is the focus of this research. In this paper we investigate how three different techniques for hyper-parameter optimization govern the learning of two variants of ECoS-based learners: The Self-Evolving Connectionist System (SECoS) and the Evolving Fuzzy Neural Network (EFuNN). Results of these experiments indicate that the Tree-structured Parzen Estimator hyper-parameter optimization algorithm works well for both SECoS and EFuNN learning on classification tasks. There are, however, unanswered questions as to the degree to which the efficacy of an appropriate hyper-parameter optimization framework can be adopted for ECoS-based learners." @default.
- W4385484672 created "2023-08-03" @default.
- W4385484672 creator A5050029919 @default.
- W4385484672 date "2023-06-18" @default.
- W4385484672 modified "2023-09-26" @default.
- W4385484672 title "Automatic Parameter Optimisation Framework for ECoS-based Models" @default.
- W4385484672 cites W1518186130 @default.
- W4385484672 cites W1969557815 @default.
- W4385484672 cites W1974758710 @default.
- W4385484672 cites W1990517717 @default.
- W4385484672 cites W2001619934 @default.
- W4385484672 cites W2005355106 @default.
- W4385484672 cites W2019625600 @default.
- W4385484672 cites W2162635690 @default.
- W4385484672 cites W2166107799 @default.
- W4385484672 cites W2888728157 @default.
- W4385484672 cites W2937450972 @default.
- W4385484672 cites W3215804261 @default.
- W4385484672 cites W4237222446 @default.
- W4385484672 cites W4243962803 @default.
- W4385484672 cites W58593274 @default.
- W4385484672 cites W60686164 @default.
- W4385484672 cites W70449568 @default.
- W4385484672 doi "https://doi.org/10.1109/ijcnn54540.2023.10191789" @default.
- W4385484672 hasPublicationYear "2023" @default.
- W4385484672 type Work @default.
- W4385484672 citedByCount "0" @default.
- W4385484672 crossrefType "proceedings-article" @default.
- W4385484672 hasAuthorship W4385484672A5050029919 @default.
- W4385484672 hasConcept C105795698 @default.
- W4385484672 hasConcept C108583219 @default.
- W4385484672 hasConcept C119857082 @default.
- W4385484672 hasConcept C120665830 @default.
- W4385484672 hasConcept C121332964 @default.
- W4385484672 hasConcept C154945302 @default.
- W4385484672 hasConcept C185429906 @default.
- W4385484672 hasConcept C192209626 @default.
- W4385484672 hasConcept C2777212361 @default.
- W4385484672 hasConcept C33923547 @default.
- W4385484672 hasConcept C41008148 @default.
- W4385484672 hasConcept C50644808 @default.
- W4385484672 hasConcept C81917197 @default.
- W4385484672 hasConcept C8521452 @default.
- W4385484672 hasConceptScore W4385484672C105795698 @default.
- W4385484672 hasConceptScore W4385484672C108583219 @default.
- W4385484672 hasConceptScore W4385484672C119857082 @default.
- W4385484672 hasConceptScore W4385484672C120665830 @default.
- W4385484672 hasConceptScore W4385484672C121332964 @default.
- W4385484672 hasConceptScore W4385484672C154945302 @default.
- W4385484672 hasConceptScore W4385484672C185429906 @default.
- W4385484672 hasConceptScore W4385484672C192209626 @default.
- W4385484672 hasConceptScore W4385484672C2777212361 @default.
- W4385484672 hasConceptScore W4385484672C33923547 @default.
- W4385484672 hasConceptScore W4385484672C41008148 @default.
- W4385484672 hasConceptScore W4385484672C50644808 @default.
- W4385484672 hasConceptScore W4385484672C81917197 @default.
- W4385484672 hasConceptScore W4385484672C8521452 @default.
- W4385484672 hasLocation W43854846721 @default.
- W4385484672 hasOpenAccess W4385484672 @default.
- W4385484672 hasPrimaryLocation W43854846721 @default.
- W4385484672 hasRelatedWork W2795261237 @default.
- W4385484672 hasRelatedWork W3014300295 @default.
- W4385484672 hasRelatedWork W3164822677 @default.
- W4385484672 hasRelatedWork W4223943233 @default.
- W4385484672 hasRelatedWork W4225161397 @default.
- W4385484672 hasRelatedWork W4312200629 @default.
- W4385484672 hasRelatedWork W4360585206 @default.
- W4385484672 hasRelatedWork W4364306694 @default.
- W4385484672 hasRelatedWork W4380075502 @default.
- W4385484672 hasRelatedWork W4380086463 @default.
- W4385484672 isParatext "false" @default.
- W4385484672 isRetracted "false" @default.
- W4385484672 workType "article" @default.